github-auth

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs users to paste or embed personal access tokens directly into commands, URLs, and echoed inputs (e.g., https://:@..., echo "<THEIR_TOKEN>" | gh auth login, export GITHUB_TOKEN=""), which would require the LLM/agent to handle or output secret values verbatim and enables exfiltration.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill instructs the agent (or user) to generate SSH keys, edit /.ssh/config, write global git credentials (/.git-credentials and ~/.gitconfig), and persist personal access tokens (including options that embed tokens in remote URLs), which changes the machine's security-sensitive state (even though it doesn't request sudo or create system users).